As a research hotspot and difficulty in the field of computer vision, pedestrian detection has been widely used in intelligent driving and traffic monitoring. The popular detection method at present uses region proposal network (RPN) to generate candidate regions, and then classifies the regions. But the RPN produces many erroneous candidate areas, causing region proposals for false positives to increase. This letter uses improved residual attention network to capture the visual attention map of images, then normalized to get the attention score map. The attention score map is used to guide the RPN network to generate more precise candidate regions containing potential target objects. The region proposals, confidence scores, and features generated by the RPN are used to train a cascaded boosted forest classifier to obtain the final results. The experimental results show that our proposed approach achieves highly competitive results on the Caltech and ETH datasets.
Rui SUN
Hefei University of Technology
Huihui WANG
Hefei University of Technology
Jun ZHANG
Hefei University of Technology
Xudong ZHANG
Hefei University of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copy
Rui SUN, Huihui WANG, Jun ZHANG, Xudong ZHANG, "Attention-Guided Region Proposal Network for Pedestrian Detection" in IEICE TRANSACTIONS on Information,
vol. E102-D, no. 10, pp. 2072-2076, October 2019, doi: 10.1587/transinf.2019EDL8027.
Abstract: As a research hotspot and difficulty in the field of computer vision, pedestrian detection has been widely used in intelligent driving and traffic monitoring. The popular detection method at present uses region proposal network (RPN) to generate candidate regions, and then classifies the regions. But the RPN produces many erroneous candidate areas, causing region proposals for false positives to increase. This letter uses improved residual attention network to capture the visual attention map of images, then normalized to get the attention score map. The attention score map is used to guide the RPN network to generate more precise candidate regions containing potential target objects. The region proposals, confidence scores, and features generated by the RPN are used to train a cascaded boosted forest classifier to obtain the final results. The experimental results show that our proposed approach achieves highly competitive results on the Caltech and ETH datasets.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2019EDL8027/_p
Copy
@ARTICLE{e102-d_10_2072,
author={Rui SUN, Huihui WANG, Jun ZHANG, Xudong ZHANG, },
journal={IEICE TRANSACTIONS on Information},
title={Attention-Guided Region Proposal Network for Pedestrian Detection},
year={2019},
volume={E102-D},
number={10},
pages={2072-2076},
abstract={As a research hotspot and difficulty in the field of computer vision, pedestrian detection has been widely used in intelligent driving and traffic monitoring. The popular detection method at present uses region proposal network (RPN) to generate candidate regions, and then classifies the regions. But the RPN produces many erroneous candidate areas, causing region proposals for false positives to increase. This letter uses improved residual attention network to capture the visual attention map of images, then normalized to get the attention score map. The attention score map is used to guide the RPN network to generate more precise candidate regions containing potential target objects. The region proposals, confidence scores, and features generated by the RPN are used to train a cascaded boosted forest classifier to obtain the final results. The experimental results show that our proposed approach achieves highly competitive results on the Caltech and ETH datasets.},
keywords={},
doi={10.1587/transinf.2019EDL8027},
ISSN={1745-1361},
month={October},}
Copy
TY - JOUR
TI - Attention-Guided Region Proposal Network for Pedestrian Detection
T2 - IEICE TRANSACTIONS on Information
SP - 2072
EP - 2076
AU - Rui SUN
AU - Huihui WANG
AU - Jun ZHANG
AU - Xudong ZHANG
PY - 2019
DO - 10.1587/transinf.2019EDL8027
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E102-D
IS - 10
JA - IEICE TRANSACTIONS on Information
Y1 - October 2019
AB - As a research hotspot and difficulty in the field of computer vision, pedestrian detection has been widely used in intelligent driving and traffic monitoring. The popular detection method at present uses region proposal network (RPN) to generate candidate regions, and then classifies the regions. But the RPN produces many erroneous candidate areas, causing region proposals for false positives to increase. This letter uses improved residual attention network to capture the visual attention map of images, then normalized to get the attention score map. The attention score map is used to guide the RPN network to generate more precise candidate regions containing potential target objects. The region proposals, confidence scores, and features generated by the RPN are used to train a cascaded boosted forest classifier to obtain the final results. The experimental results show that our proposed approach achieves highly competitive results on the Caltech and ETH datasets.
ER -